arXiv:2607. 01144v1 Announce Type: cross Abstract: While generative models have enabled training-free reward alignment, current methods typically excel in local exploration within narrow regions of the underlying distribution.
arXiv:2609.37227v1 Announce Type: new Abstract: Inference-time steering adapts pretrained diffusion and flow-based models to new tasks, e.g., to generate samples from a conditional distribution or sa...
arXiv:2607. 02915v1 Announce Type: cross Abstract: In many scientific and engineering domains, maximizing discovery within a limited sampling budget demands strategic, observation-guided exploration.
arXiv:2607. 02834v1 Announce Type: new Abstract: Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures.
arXiv:2608. 13800v1 Announce Type: new Abstract: Transition path sampling (TPS) aims to efficiently generate rare molecular transition trajectories between metastable states and is essential for understanding biomolecular mechanisms.
VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion proposes a new inference-time framework that improves steering of frozen masked discrete diffusion models. By reducing the variance of guidance estimates, applying reward tilting to clean-token logits, and adapting the selection temperature at each step, VGAS addresses three default choices in existing pipelines. Experiments on regulatory DNA, protein, and small-molecule benchmarks show that VGAS achieves the best training-free reward performance and matches or surpasses reward-fine-tuned generators.
arXiv:2606. 08375v1 Announce Type: new Abstract: All-atom generative modeling of 3D biomolecular complexes has emerged as the dominant paradigm for predicting the structure of proteins and protein-ligand systems.
arXiv:2510. 11711v3 Announce Type: replace Abstract: This paper proposes a synergy of amortised and particle-based methods for sampling from distributions defined by unnormalised density functions.
arXiv:2510. 09976v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of supervised data.
The paper introduces GRAS, a method that improves training‑free reward alignment for discrete diffusion models by reducing variance in guided proposals and adapting the resampling temperature during search. It achieves this without adding denoiser cost, using Rao‑Blackwellized estimates for differentiable rewards and a leave‑one‑out baseline for non‑differentiable ones. Experiments on regulatory DNA and protein design show GRAS outperforms existing training‑free techniques and rivals reward‑fine‑tuned models.
arXiv:2601. 14430v2 Announce Type: replace-cross Abstract: Controlling generative models is computationally expensive.
arXiv:2609.15123v1 Announce Type: cross Abstract: Flow-based policies offer an expressive representation for online reinforcement learning, but conventional flow matching requires samples drawn from...
arXiv:2608. 08770v1 Announce Type: cross Abstract: Diffusion models are increasingly used as controllable samplers, whose generations can be steered at inference time according to a chosen reward function.